{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T17:55:26Z","timestamp":1769277326605,"version":"3.49.0"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T00:00:00Z","timestamp":1726531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T00:00:00Z","timestamp":1726531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]},{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]},{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]},{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]},{"name":"Humanities and Social Sciences of the Ministry of Education in China","award":["22YJAZH002"],"award-info":[{"award-number":["22YJAZH002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00371-024-03604-y","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T13:43:13Z","timestamp":1726666993000},"page":"3309-3327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["3D human pose estimation using spatiotemporal hypergraphs and its public benchmark on opera videos"],"prefix":"10.1007","volume":"41","author":[{"given":"Xingquan","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"LiZhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YiJie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"3604_CR1","unstructured":"Li, W., Cheng, X.X.: Research on the analysis and regeneration of cultural memory of opera based on cross-border thinking. Sichuan Theatre. 36\u201339 (2022)"},{"key":"3604_CR2","unstructured":"Xu, B.: Field migration and core features of Chinese opera communication. Media. 91\u201393 (2022)"},{"key":"3604_CR3","unstructured":"Qi, M.: The three-dimensional characteristics of artistic innovation in Chinese opera music. Sichuan Theatre. 53\u201356 (2022)"},{"key":"3604_CR4","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., et al.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"3604_CR5","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/TMM.2020.2999181","volume":"23","author":"A Kamel","year":"2021","unstructured":"Kamel, A., Sheng, B., Li, P., et al.: Hybrid refinement-correction heatmaps for human pose estimation. IEEE Trans. Multimed. 23, 1330\u20131342 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3604_CR6","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"N Jiang","year":"2023","unstructured":"Jiang, N., Sheng, B., Li, P., et al.: PhotoHelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multimed. 25, 2226\u20132238 (2023)","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"3604_CR7","doi-asserted-by":"publisher","first-page":"2774","DOI":"10.1109\/TSMC.2019.2916896","volume":"51","author":"K Aouaidjia","year":"2021","unstructured":"Aouaidjia, K., Sheng, B., Li, P., et al.: Efficient body motion quantification and similarity evaluation using 3-D joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51(5), 2774\u20132788 (2021)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"3604_CR8","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.ijinfomgt.2018.03.004","volume":"45","author":"A Karambakhsh","year":"2019","unstructured":"Karambakhsh, A., Kamel, A., Sheng, B., et al.: Deep gesture interaction for augmented anatomy learning. Int. J. Inf. Manag. 45, 328\u2013336 (2019)","journal-title":"Int. J. Inf. Manag."},{"key":"3604_CR9","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu, M., Liu, H., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn. 68, 346\u2013362 (2017)","journal-title":"Pattern Recogn."},{"issue":"4","key":"3604_CR10","doi-asserted-by":"publisher","first-page":"2476","DOI":"10.1109\/TII.2020.3000204","volume":"17","author":"R Ali","year":"2020","unstructured":"Ali, R., Sheng, B., Li, P., et al.: Optic disk and cup segmentation through fuzzy broad learning system for glaucoma screening. IEEE Trans. Industr. Inf. 17(4), 2476\u20132487 (2020)","journal-title":"IEEE Trans. Industr. Inf."},{"issue":"3","key":"3604_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3446370","volume":"54","author":"M Hassanin","year":"2021","unstructured":"Hassanin, M., Khan, S., Tahtali, M.: Visual affordance and function understanding: a survey. ACM Comput. Surv. (CSUR) 54(3), 1\u201335 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"11","key":"3604_CR12","first-page":"13489","volume":"45","author":"A Kamel","year":"2023","unstructured":"Kamel, A., Sheng, B., Li, P., et al.: MNGNAS: distilling adaptive combination of multiple searched networks for one-shot neural architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13489\u201313508 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3604_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta, D., Sridhar, S., Sotnychenko, O., et al.: VNect: real-time 3D human pose estimation with a single RGB camera. ACM Trans. Graph. 36(4), 1\u201314 (2017)","journal-title":"ACM Trans. Graph."},{"key":"3604_CR14","doi-asserted-by":"crossref","unstructured":"Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: Computer vision\u2013ACCV 2014: 12th Asian conference on computer vision, Singapore, pp. 332\u2013347 (2015)","DOI":"10.1007\/978-3-319-16808-1_23"},{"key":"3604_CR15","doi-asserted-by":"crossref","unstructured":"Ma, X., Su, J., Wang, C., et\u00a0al.: Context modeling in 3D human pose estimation: a unified perspective. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 6238\u20136247 (2021)","DOI":"10.1109\/CVPR46437.2021.00617"},{"key":"3604_CR16","doi-asserted-by":"crossref","unstructured":"Sun, X., Xiao, B., Wei, F., et\u00a0al.: Integral human pose regression. In: Proceedings of the European conference on computer vision (ECCV), pp. 529\u2013545 (2018)","DOI":"10.1007\/978-3-030-01231-1_33"},{"issue":"3\u20134","key":"3604_CR17","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2078","volume":"33","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Wang, C.: Parallel-branch network for 3D human pose and shape estimation in video. Comput. Animat. Virtual Worlds 33(3\u20134), e2078 (2022)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"3604_CR18","doi-asserted-by":"crossref","unstructured":"Xu, T., Takano, W.: Graph stacked hourglass networks for 3D human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 16105\u201316114 (2021)","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"3604_CR19","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., et\u00a0al.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"3604_CR20","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1109\/TMM.2022.3141231","volume":"25","author":"W Li","year":"2022","unstructured":"Li, W., Liu, H., Ding, R., et al.: Exploiting temporal contexts with strided transformer for 3d human pose estimation. IEEE Trans. Multimed. 25, 1282\u20131293 (2022)","journal-title":"IEEE Trans. Multimed."},{"issue":"7","key":"3604_CR21","doi-asserted-by":"publisher","first-page":"2417","DOI":"10.1007\/s00371-021-02120-7","volume":"38","author":"P Verma","year":"2022","unstructured":"Verma, P., Srivastava, R.: Two-stage multi-view deep network for 3D human pose reconstruction using images and its 2D joint heatmaps through enhanced stack-hourglass approach. Vis. Comput. 38(7), 2417\u20132430 (2022)","journal-title":"Vis. Comput."},{"issue":"5","key":"3604_CR22","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1109\/TMM.2018.2818329","volume":"20","author":"P Wang","year":"2018","unstructured":"Wang, P., Li, W., Gao, Z., et al.: Depth pooling based large-scale 3-D action recognition with convolutional neural networks. IEEE Trans. Multimed. 20(5), 1051\u20131061 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"3604_CR23","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., et\u00a0al.: A simple yet effective baseline for 3D human pose estimation. In: IEEE\/CVF international conference on computer vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"3604_CR24","unstructured":"Kudo, Y., Ogaki, K., Matsui, Y., et\u00a0al.: Unsupervised adversarial learning of 3D human pose from 2D joint locations. arXiv:1803.08244 (2018)"},{"key":"3604_CR25","doi-asserted-by":"crossref","unstructured":"Lin, J., Lee, G, H.: Multi-view multi-person 3D pose estimation with plane sweep stereo. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 11886\u201311895 (2021)","DOI":"10.1109\/CVPR46437.2021.01171"},{"key":"3604_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., et\u00a0al.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"3604_CR27","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, S., Xiong, Y., et\u00a0al.: Motion guided 3D pose estimation from videos. In: European conference on computer vision (ECCV), pp. 764\u2013780 (2020)","DOI":"10.1007\/978-3-030-58601-0_45"},{"key":"3604_CR28","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Liu, J., et\u00a0al.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"3604_CR29","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yang, B., Wang, B., et\u00a0al.: Occlusion-aware networks for 3D human pose estimation in video. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), 723\u2013732 (2019)","DOI":"10.1109\/ICCV.2019.00081"},{"key":"3604_CR30","doi-asserted-by":"crossref","unstructured":"Liu, R., Shen, J., Wang, H., et\u00a0al.: Attention mechanism exploits temporal contexts: real-time 3D human pose reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 5064\u20135073 (2020)","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"3604_CR31","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., et\u00a0al.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"3604_CR32","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., et\u00a0al.: Human 3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"issue":"4\u20135","key":"3604_CR33","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., et al.: An investigation of 3D human pose estimation for learning Tai Chi: a human factor perspective. Int. J. Hum.-Comput. Interact. 35(4\u20135), 427\u2013439 (2019)","journal-title":"Int. J. Hum.-Comput. Interact."},{"issue":"4","key":"3604_CR34","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s00371-021-02229-9","volume":"38","author":"S Zeghoud","year":"2022","unstructured":"Zeghoud, S., Ali, S.G., Ertugrul, E., et al.: Real-time spatial normalization for dynamic gesture classification. Vis. Comput. 38(4), 1345\u20131357 (2022)","journal-title":"Vis. Comput."},{"key":"3604_CR35","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yang, Q., Wang, J., et\u00a0al.: PSVT: end-to-end multi-person 3D pose and shape estimation with progressive video transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp . 21254\u201321263 (2023)","DOI":"10.1109\/CVPR52729.2023.02036"},{"key":"3604_CR36","doi-asserted-by":"crossref","unstructured":"Ye, S., Zhang, Y., Hu, J., et\u00a0al.: DistilPose: Tokenized pose regression with heatmap distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 2163\u20132172 (2023)","DOI":"10.1109\/CVPR52729.2023.00215"},{"key":"3604_CR37","doi-asserted-by":"crossref","unstructured":"Huang, L., Li, Y., Tian, H., et\u00a0al.: Semi-supervised 2D human pose estimation driven by position inconsistency pseudo label correction module. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), 693\u2013703 (2023)","DOI":"10.1109\/CVPR52729.2023.00074"},{"key":"3604_CR38","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: European conference on computer vision (ECCV), 282\u2013298 (2020)","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"3604_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., et\u00a0al.: 3D human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"3604_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., et\u00a0al.: Semantic graph convolutional networks for 3D human pose regression. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"3604_CR41","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"3604_CR42","doi-asserted-by":"crossref","unstructured":"Zou, Z., Tang, W.: Modulated graph convolutional network for 3D human pose estimation. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp. 11477\u201311487 (2021)","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"3604_CR43","doi-asserted-by":"crossref","unstructured":"Hu, W., Zhang, C., Zhan, F., et\u00a0al.: Conditional directed graph convolution for 3D human pose estimation. In: Proceedings of the 29th ACM international conference on multimedia, 602\u2013611 (2021)","DOI":"10.1145\/3474085.3475219"},{"key":"3604_CR44","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3604_CR45","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of international conference on learning representations (ICLR), (2020)"},{"key":"3604_CR46","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Huang, F., et\u00a0al.: SRNet: improving generalization in 3D human pose estimation with a split-and-recombine method. In: European conference on computer vision (ECCV), pp. 507\u2013523 (2020)","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"3604_CR47","doi-asserted-by":"crossref","unstructured":"Hassanin, M., Khamiss, A., Bennamoun, M., et\u00a0al.: CrossFormer: cross spatio-temporal transformer for 3D human pose estimation. arXiv:2203.13387 (2022)","DOI":"10.2139\/ssrn.4213439"},{"key":"3604_CR48","doi-asserted-by":"crossref","unstructured":"Diaz-Arias, A., Shin, D.: ConvFormer: parameter reduction in transformer models for 3D human pose estimation by leveraging dynamic multi-headed convolutional attention. arXiv:2304.02147 (2023)","DOI":"10.1007\/s00371-023-02936-5"},{"issue":"4\u20135","key":"3604_CR49","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1080\/10447318.2018.1543081","volume":"35","author":"A Kamel","year":"2019","unstructured":"Kamel, A., Liu, B., Li, P., Sheng, B.: An investigation of 3D human pose estimation for learning Tai Chi: a human factor perspective. Int. J. Human-Comput. Interact. 35(4\u20135), 427\u2013439 (2019)","journal-title":"Int. J. Human-Comput. Interact."},{"key":"3604_CR50","doi-asserted-by":"crossref","unstructured":"Yan, X., Song, T., Jiao, Y., et\u00a0al.: Spatio-temporal hypergraph learning for next POI recommendation. In: Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval, pp. 403\u2013412 (2023)","DOI":"10.1145\/3539618.3591770"},{"key":"3604_CR51","doi-asserted-by":"crossref","unstructured":"Su, Y., Tan, Y., Xing, M., et\u00a0al.: VPE-WSVAD: visual prompt exemplars for weakly-supervised video anomaly detection. Knowl.-Based Syst. 111978 (2024)","DOI":"10.1016\/j.knosys.2024.111978"},{"key":"3604_CR52","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, Z., Zhang, B., et\u00a0al.: MGFN: magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection. In: Proceedings of the AAAI conference on artificial intelligence. 37(1), 387\u2013395 (2023)","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"3604_CR53","doi-asserted-by":"crossref","unstructured":"Su, Y., Tan, Y., An, S., et\u00a0al.: Anomalies cannot materialize or vanish out of thin air: a hierarchical multiple instance learning with position-scale awareness for video anomaly detection. Expert Syst. Appl. 124392 (2024)","DOI":"10.1016\/j.eswa.2024.124392"},{"key":"3604_CR54","doi-asserted-by":"crossref","unstructured":"Wang, R., Wu, W., Wang, X.: Enhancing multi-scale information exchange and feature fusion for human pose estimation. Vis. Comput., 1\u201315 (2022)","DOI":"10.1007\/s00371-022-02623-x"},{"issue":"1","key":"3604_CR55","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","volume":"32","author":"T Chen","year":"2021","unstructured":"Chen, T., Fang, C., Shen, X., et al.: Anatomy-aware 3D human pose estimation with bone-based pose decomposition. IEEE Trans. Circuits Syst. Video Technol. 32(1), 198\u2013209 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3604_CR56","doi-asserted-by":"crossref","unstructured":"Furtado, J.S., Liu, H.H.T., Lai, G., et\u00a0al.: Comparative analysis of optitrack motion capture systems. Adv. Motion Sens. Control Robot. Appl., 15\u201331 (2019)","DOI":"10.1007\/978-3-030-17369-2_2"},{"key":"3604_CR57","doi-asserted-by":"crossref","unstructured":"Li, H., Shi, B., Dai, W., et\u00a0al.: Pose-oriented transformer with uncertainty-guided refinement for 2D-to-3D human pose estimation. In: Proceedings of the AAAI conference on artificial intelligence. 37(1), 1296\u20131304 (2023)","DOI":"10.1609\/aaai.v37i1.25213"},{"key":"3604_CR58","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L, G., Fan, Z., et\u00a0al.: DiffPose: toward more reliable 3D pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13041\u201313051 (2023)","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"3604_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, F., Yin, J., Li, P.: Lifting by image\u2013leveraging image cues for accurate 3D human pose estimation. arXiv:2312.15636 (2023)","DOI":"10.1609\/aaai.v38i7.28596"},{"key":"3604_CR60","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wang, W., Tian, Y.: GraFormer: graph-oriented transformer for 3D pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 20438\u201320447 (2022)","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"3604_CR61","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., et\u00a0al.: MHFormer: multi-hypothesis transformer for 3D human pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13147\u201313156 (2022)","DOI":"10.1109\/CVPR52688.2022.01280"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03604-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03604-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03604-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T09:09:21Z","timestamp":1741597761000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03604-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,17]]},"references-count":61,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3604"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03604-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,17]]},"assertion":[{"value":"6 August 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"1. Author Xingquan Cai declares that he has no Conflict of interest. 2. Author Haoyu Zhang declares that he has no Conflict of interest. 3. Author Lizhe Chen declares that he has no Conflict of interest. 4. Author Yijie Wu declares that he has no Conflict of interest. 5. Author Haiyan Sun declares that he has no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}